Machine Learning to Recognise and Identify Bird Species from Radar Data

About this project

The Humber estuary is rich in resident bird life and represents a significant corridor for migratory species. However, it is also a highly dynamic and industrialised landscape thus presents a mix of risks, challenges and benefits to the birds that use it. Conversely, the presence of resident and migratory birds along the estuary raises issues for industrial development and, potentially, human and livestock health. In partnership with the Animal & Plant Health Agency we share an ambition to create a new, vibrant research community with an explicit focus on bird ecology and behaviour in order to answer pure and applied questions regarding the use of the landscape by birds and interactions with human interests. Central to the work programme are three PhD Scholarships, all of which will be underpinned by the deployment of a bird detection radar and mobile laboratory at sites at which birds can be directly observed and sampled.

Machine learning to recognise and identify bird species from radar data

Existing systems for interpreting collected radar data for bird detection rely heavily on human interpretation and annotation. The use of such annotated data can be used to train machine learning software to perform this task. The project will investigate a number of challenges. The radar data gathered are prone to noise and clutter. Filters need to be designed and implemented that remove such noise and discriminate between bird and non-bird moving targets. The use of state-of-the-art deep learning techniques, such as convolutional neural nets and support vector machines, can be used here. Swarm algorithms can then be investigated in an effort to provide species level identification. The use of intelligent interfaces will enable the data, and its interpretations, to be visualised and interrogated. These advances will enable far deeper insight into the radar data, offering greater efficacy and efficiency to the other projects within this cluster and to future bird radar projects.


You are strongly advised to contact a potential supervisor and to discuss your research proposal, well before you submit an application. Please refer to the School of Environmental Sciences research pages.

If you have any queries, please email Dr Alastair Ward.

Next steps


To celebrate the University's research successes, the University of Hull is offering a full-time UK/EU PhD Scholarship or International Fees Bursary.

Entry requirements

 The successful candidate will be a competent numerical scientist with experience of machine learning, excellent skills in programming and at least an interest in bird ecology and behaviour.

Applicants should have at least a 2.1 undergraduate degree in Biology/Ecology (projects 2 and 3), or Computer Science/Mathematics (project 1) or related discipline, together with relevant research experience. It is anticipated that the successful applicant will have a 1st class undergraduate degree or Masters level qualification. 

How to apply

Applications for scholarship consideration at the University of Hull should be made through the Postgraduate Application system.

On the second page of your application, please select “Graduate Scholarship” as the type of scholarship you are applying for. 

Applicants are strongly encouraged to first identify and contact a potential supervisor.

Apply now

Application deadline: Monday 4 June


Full-time UK/EU PhD Scholarships will include fees at the ‘home/EU' student rate and maintenance (£14,553 in 2017/18) for three years, depending on satisfactory progress.

Full-time International Fee PhD Studentships will include full fees at the International student rate for three years, dependent on satisfactory progress.